6 papers
MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration
Wenzhang Sun, Zhenyu Wang, Zhangchi Hu +3
Generating long-form audio-visual stories from a short user prompt remains challenging due to an intent-execution gap, where high-level narrative intent must be preserved across co…
DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation
Xiangchen Yin, Jiahui Yuan, Zhangchi Hu +5
Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled V…
Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding
Bowei Pu, Chuanbin Liu, Yifan Ge +5
Video Large Language Models improve reasoning over complex videos by generating intermediate reasoning text. However, reliable reasoning depends on accurate video perception. In ex…
DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering
Jie Chen, Zhangchi Hu, Peixi Wu +3
Dynamic scene reconstruction is a long-term challenge in 3D vision. Existing plane-based methods in dynamic Gaussian splatting suffer from an unsuitable low-rank assumption, causin…
Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection
Zhangchi Hu, Peixi Wu, Jie Chen +5
Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes. However…
Efficient Spiking Point Mamba for Point Cloud Analysis
Peixi Wu, Bosong Chai, Menghua Zheng +6
Bio-inspired Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. However, existing 3D SNNs have struggled with long-range depende…